Disappointing upgrade from 4080 + 5800x to 4080 + 5950x. No significant change in performance, in fact it’s slightly slower on most of the benchmarks. Slightly slower overall in real life processing too, for most video resolutions. Unchanged system settings, updated BIOS with previous settings restored.
I do see lower CPU usages on real world processing, with much greater headroom thus allowing me to easliy run 2 or 3 processes in parallel so there is a net gain of 20% to 50% on bulk processing, but for single processes e.g. just doing one long video, there’s no gain unless I first spend time splitting it into two halves. I did suspect all this as 5950x has a lower clock speed than 5800x but still, disappointed not to see gains in single processing.
5800x
Topaz Video AI v4.0.9 [new bios]
System Information
OS: Windows v10.22
CPU: AMD Ryzen 7 5800X 8-Core Processor 31.906 GB
GPU: NVIDIA GeForce RTX 4080 15.688 GB
Processing Settings
device: -2 vram: 0.95 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 30.38 fps 2X: 12.02 fps 4X: 02.77 fps
Iris 1X: 34.25 fps 2X: 13.88 fps 4X: 03.37 fps
Proteus 1X: 21.55 fps 2X: 10.29 fps 4X: 02.67 fps
Gaia 1X: 10.88 fps 2X: 07.31 fps 4X: 03.02 fps
Nyx 1X: 12.89 fps 2X: 10.90 fps
4X Slowmo Apollo: 35.44 fps APFast: 52.74 fps Chronos: 24.42 fps CHFast: 27.31 fps
5950x
Topaz Video AI v4.0.9
System Information
OS: Windows v10.22
CPU: AMD Ryzen 9 5950X 16-Core Processor 31.904 GB
GPU: NVIDIA GeForce RTX 4080 15.688 GB
Processing Settings
device: -2 vram: 0.99 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 27.34 fps 2X: 11.96 fps 4X: 02.75 fps
Iris 1X: 30.78 fps 2X: 14.10 fps 4X: 03.44 fps
Proteus 1X: 20.66 fps 2X: 10.05 fps 4X: 02.67 fps
Gaia 1X: 10.77 fps 2X: 07.72 fps 4X: 03.02 fps
Nyx 1X: 12.76 fps 2X: 10.88 fps
4X Slowmo Apollo: 32.56 fps APFast: 50.83 fps Chronos: 23.84 fps CHFast: 28.07 fps
